From amazon-bestsellers-summary
Amazon 商品完整 HTML 页面的分块器。读取 ≈2MB 的完整详情页 HTML,按稳定 DOM id 切出 4 个子 HTML(ppd / customer_reviews / product_details / aplus)。当 agent 需要对完整 HTML 进行分块切分时调度此技能。
How this skill is triggered — by the user, by Claude, or both
Slash command
/amazon-bestsellers-summary:amazon-chunkerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
读取完整 HTML,找出 Amazon 稳定的大块 DOM `id`,写好分块器(`chunker.py`),利用分块器切出 4 个子 HTML 文件,并验证切分是否正确合理。
读取完整 HTML,找出 Amazon 稳定的大块 DOM id,写好分块器(chunker.py),利用分块器切出 4 个子 HTML 文件,并验证切分是否正确合理。
| 块名 | 主 selector | 备选 selector | 内容 |
|---|---|---|---|
ppd | #ppd | #dp-container | 标题/价格/评分/buybox/变体/卖点/图片 |
customer_reviews | #customerReviews | #reviewsMedley | 评分分布 + 用户评论 |
product_details | #productDetails_feature_div | #detailBullets_feature_div | 规格参数表 |
aplus | #aplus | #aplusBrandStory_feature_div | A+ 品牌内容/对比表/图片 |
BeautifulSoup(html, "lxml") 解析完整 HTMLsoup.select_one()<script> 标签,其他原样保留<block_name>.htmlMCP scraper 产出:{workspace}/products/{ASIN}/product.html
products/{ASIN}/product.html 样本文件(优先 Top1/Top25)id 的顶层节点,对比多个样本找出共有块chunker/static_chunker.py 中每个 block 的 selector,生成分块器代码 + 测试chunker/static_chunker.py — 分块器实现tests/test_static_chunker.py — 分块器测试Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub mengsi16/amazon-bestsellers-summary-agent